ComfyUI  >  Nodes  >  ComfyUI Impact Pack >  ONNX Detector (SEGS/legacy) - use BBOXDetector

ComfyUI Node: ONNX Detector (SEGS/legacy) - use BBOXDetector

Class Name

ONNXDetectorSEGS

Category
ImpactPack/Detector
Author
Dr.Lt.Data (Account age: 458 days)
Extension
ComfyUI Impact Pack
Latest Updated
6/19/2024
Github Stars
1.4K

How to Install ComfyUI Impact Pack

Install this extension via the ComfyUI Manager by searching for  ComfyUI Impact Pack
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI Impact Pack in the search bar
After installation, click the  Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • High-speed GPU machines
  • 200+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 50+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

ONNX Detector (SEGS/legacy) - use BBOXDetector Description

Facilitates object detection and segmentation using ONNX models for AI art and image processing applications.

ONNX Detector (SEGS/legacy) - use BBOXDetector:

The ONNXDetectorSEGS node is designed to facilitate object detection and segmentation tasks using ONNX models. This node leverages pre-trained ONNX models to detect objects within an image and generate segmentation masks, which are essential for various AI art and image processing applications. By providing a streamlined interface for object detection, the ONNXDetectorSEGS node allows you to easily integrate advanced detection capabilities into your workflows, enhancing the precision and quality of your artistic projects. The node's primary function is to process an input image and produce segmentation results based on the specified parameters, making it a powerful tool for artists looking to incorporate AI-driven segmentation into their creative processes.

ONNX Detector (SEGS/legacy) - use BBOXDetector Input Parameters:

onnx_detector

This parameter specifies the ONNX detector model to be used for the detection task. The ONNX detector is a pre-trained model that has been optimized for object detection and segmentation tasks. By selecting an appropriate ONNX detector, you can ensure that the node performs accurate and efficient detection on the input image.

image

The image parameter is the input image that you want to process using the ONNX detector. This image will be analyzed by the detector to identify and segment objects within it. The quality and resolution of the input image can significantly impact the accuracy of the detection results.

threshold

The threshold parameter is a floating-point value that determines the confidence level required for an object to be considered detected. It ranges from 0.0 to 1.0, with a default value of 0.8. A higher threshold means that only objects with higher confidence scores will be detected, which can reduce false positives but may also miss some objects.

dilation

The dilation parameter is an integer that specifies the amount of dilation to be applied to the detected segmentation masks. It ranges from -512 to 512, with a default value of 10. Dilation can help to refine the edges of the segmentation masks, making them more accurate and visually appealing.

crop_factor

The crop_factor parameter is a floating-point value that determines the scaling factor for cropping the detected objects. It ranges from 0.5 to 100, with a default value of 1.0. This parameter allows you to adjust the size of the cropped regions around the detected objects, which can be useful for focusing on specific areas of interest.

drop_size

The drop_size parameter is an integer that specifies the minimum size of objects to be considered for detection. It ranges from 1 to the maximum resolution of the input image, with a default value of 10. This parameter helps to filter out small, irrelevant objects, ensuring that only significant objects are detected and segmented.

ONNX Detector (SEGS/legacy) - use BBOXDetector Output Parameters:

SEGS

The SEGS output parameter contains the segmentation results generated by the ONNX detector. This output includes the segmented regions of the input image, which can be used for further processing or visualization. The segmentation results are essential for tasks such as object recognition, image editing, and AI-driven artistic effects.

ONNX Detector (SEGS/legacy) - use BBOXDetector Usage Tips:

  • Adjust the threshold parameter to balance between detecting all possible objects and minimizing false positives. A higher threshold will result in fewer, but more confident detections.
  • Use the dilation parameter to refine the edges of the segmentation masks. Positive values will expand the masks, while negative values will contract them.
  • Experiment with the crop_factor to focus on different areas of the detected objects. Increasing the crop factor can help to include more context around the objects.
  • Set the drop_size parameter to filter out small, irrelevant objects. This can help to improve the clarity and relevance of the segmentation results.

ONNX Detector (SEGS/legacy) - use BBOXDetector Common Errors and Solutions:

"Model not found"

  • Explanation: The specified ONNX model could not be located.
  • Solution: Ensure that the model name is correct and that the model file is located in the appropriate directory.

"Invalid image format"

  • Explanation: The input image is not in a supported format.
  • Solution: Verify that the input image is in a compatible format (e.g., JPEG, PNG) and try again.

"Threshold value out of range"

  • Explanation: The threshold parameter is set outside the allowed range of 0.0 to 1.0.
  • Solution: Adjust the threshold value to be within the specified range.

"Dilation value out of range"

  • Explanation: The dilation parameter is set outside the allowed range of -512 to 512. - Solution: Adjust the dilation value to be within the specified range.

"Drop size exceeds image resolution"

  • Explanation: The drop_size parameter is set to a value larger than the resolution of the input image.
  • Solution: Set the drop_size parameter to a value within the resolution limits of the input image.

ONNX Detector (SEGS/legacy) - use BBOXDetector Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI Impact Pack
RunComfy

© Copyright 2024 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals.